Progressive Re-ranking for Multimodal Retrieval-Augmented Generation via Curriculum Learning

Retrieval-augmented generation (RAG) can enhance large language models (LLMs) by providing external knowledge and helping reduce hallucinations. In multimodal RAG, however, retrieval remains challenging because a single retriever may fail to capture fine-grained multimodal semantics, and visually or semantically similar entities may still contain misleading information for answer generation. We propose a progressive multimodal re-ranking framework with curriculum learning to improve CLIPbased visual coarse-grained retrieval. Our framework progressively refines retrieval results through two stages: fine-grained sectionlevel re-ranking and multimodal section reassessment. To better align re-ranking with multimodal queries, we introduce a curriculumlearning strategy that trains the model with hard negatives that are visually or semantically similar but contain misleading information. Experiments on InfoSeek and Enc-VQA show that our method achieves state-of-the-art answer accuracy and competitive retrieval performance.